展示HN: KeyID – 适用于AI代理(MCP)的免费电子邮件和电话基础设施
Show HN: KeyID – Free email and phone infrastructure for AI agents (MCP)

原始链接: https://keyid.ai/

KeyID 提供了一种部署 AI 代理来处理现实世界任务的解决方案,这些任务需要电子邮件、短信和网站验证——无需承担典型的成本和复杂性。与 Gmail 或 AgentMail 等服务不同,KeyID **最多可免费用于 1,000 个独立的代理帐户**,而非按消息计费,这对于目前正在支付每邮箱费用的团队来说极具吸引力。 它支持单个代理和大型集群,能够实现真实网站上的自动化注册、恢复流程和双因素身份验证。至关重要的是,**无需人工设置或 API 密钥**即可使代理进行通信;它专为代理原生基础设施而设计。 KeyID 处理发送*和*接收消息,使其适用于支持、外联和自动化。针对流行的代理(如 MCP、Claude 和 Playwright)的设置指南已准备就绪,提供了一条简化的路径,可以部署具有真实通信身份的代理。

## KeyID:AI 代理的电子邮件和电话基础设施 KeyID (keyid.ai) 为需要电子邮件和电话号码的 AI 代理提供免费的基础设施解决方案,用于例如注册和验证等任务。它解决的核心问题是,在没有昂贵付费服务或易被屏蔽的一次性选项的情况下,以编程方式获取可靠电子邮件地址的困难。 KeyID 通过一次 API 调用提供真实的电子邮件地址和电话号码,利用 Ed25519 密钥对进行身份验证 – 从而无需 API 密钥。代理可以发送/接收电子邮件,自动提取验证码,并管理多步骤注册。 该服务通过共享的、轮换的域名池免费提供高达 1,000 个帐户,该域名池由 KeyID 管理以确保可传递性和信誉。超出此数量,将计划提供具有专用域名的付费套餐。滥用行为通过基于密钥对的身份验证、每个代理的信誉跟踪以及维护共享、可靠域名池的激励措施来缓解。 KeyID 是开源的 (github.com/KeyID-AI/KeyID),并提供 Javascript 和 Python 的 SDK。
相关文章

原文

Answers teams ask before they move one agent or a whole fleet onto real inboxes, SMS, and website verification work.

Is KeyID really free at 1,000 accounts?

Yes. The homepage claim is about 1,000 separate accounts, not 1,000 messages. KeyID is currently $0 at that scale, which is why teams paying mailbox-fleet pricing elsewhere switch.

Is this for one agent, or for teams running fleets?

Both. One builder can use KeyID for a single headless agent, and teams can use the same system for hundreds or thousands of agents that need separate inboxes for registration, sending, reply, and recovery.

Can agents actually use this on real websites that send email or SMS verification?

Yes. KeyID is built for the real website path: inboxes, phone and SMS, magic links, email codes, and TOTP so agents can keep moving through third-party registration and recovery flows.

Why not use Gmail, Google Workspace, AgentMail, or outreach tools?

Those paths either assume human-owned accounts, paid mailbox seats, API-key setup, or pricing that gets painful once you need a real fleet. KeyID is aimed at agent-native infrastructure instead. The full breakdown is on the compare page.

Do I need a human setup, dashboard, or API key before an agent can use it?

No. The goal is zero human setup in the critical path. Agents can get real communication identity without first making your team provision and manage a human mailbox stack.

Where do I find MCP, Claude, Cursor, Lovable, Replit, OpenClaw, or Playwright setup?

See the For agents section below. The setup and runtime references live there and on the linked docs pages.

Can agents send or reply from these accounts too?

Yes. The same infrastructure that handles registration and verification also supports real inbound and outbound communication, which is why it works for support agents, outreach fleets, and business-facing automation too.

联系我们 contact @ memedata.com